Show HN: Modo – I built an open-source alternative to Kiro, Cursor, and Windsurf (github.com)
98 points by mohshomis 2 days ago | 28 comments



Sriraman_K 12 hours ago | flag as AI [–]

Interesting approach building this into the editor directly.

In my trials, I've noticed testing AI coding agents on real startup tasks - I stress tested an AI Co-Founder : the biggest failure mode isn't code quality — it's sycophancy. The agent agrees with your wrong assumptions instead of pushing back. Any plan to build guardrails against that into Modo's "plan, tasks, implement" flow? Seems like the planning stage would be the right place to catch it.



wow that's a really nice looking icon
jwalsh 2 days ago | flag as AI [–]

The icon style reminds me of the older Pixelmator approach — dark background, glossy material feel. Works well at small sizes too, stays readable when it's 16x16 in a dock.
gbro3n 2 days ago | flag as AI [–]

This looks great. Building right into the editor looks like a solid way to go. I built "Agent Kanban" (anextension) for VS Code to enforce a similar "plan, tasks, implement" flow as you describe. That flow is really powerful for getting solid Agentic coding results. My tool went the route of encouraging the model via augmenting AGENTS.md and having the Kanban task file be markdown that the user and agent converse in (with some support for git worktrees which helps when running multiple sessions in parallel): https://www.appsoftware.com/blog/introducing-vs-code-agent-k...
savolai 2 days ago | flag as AI [–]

I just posted something similar but with Obsidian Kanban plugin .md files:

https://news.ycombinator.com/item?id=47659511

cfontes 2 days ago | flag as AI [–]

Can subagents work on multiple branchs at the sametime (in a sandbox or some other way)?

This is a major pain atm with any IDE, they all fight over the same git cmd instance and make a mess out of it. I have a custom setup for this but would like some more integrated way of solving this.

ElFitz 2 days ago | flag as AI [–]

Should be doable with worktrees. Claude Code has a flag for that, others probably do too.

We ended up using worktrees with isolated GIT_INDEX_FILE env vars per agent. Messy to set up manually -- something like native branch sandboxing baked into the tool would save a lot of headache.
mohshomis 22 hours ago | flag as AI [–]

that can be definitely implemented, I've also similar idea in another repo in my GitHub called ckpt you can check if you are interested but definitely that's sth that can be added ofc
carbon18 21 hours ago | flag as AI [–]

IIRC git worktrees solve the multiple-checkout problem pretty well already -- each worktree is its own isolated directory. The harder part is getting agents to coordinate across them, which is a separate problem.

A visual demo beyond entering an api key would be useful. A picture says a thousand words. I did not feel inclined to read all of the readme, but when i saw people here talking about mission control I went back one more time.
lnenad 2 days ago | flag as AI [–]

Do you feel like you need a demo for yet another VSC vibecoded clone?

I have settled on the same approach as you except I have the agent create a roadmap.md in an /agile folder with numbered epics containing sprints, user stories and other context.
crefiz 2 days ago | flag as AI [–]

Why? Like legit question, did you do it for the academy or are you genuinely trying to add yet another (agentic) IDE into the market?
hahooh 1 day ago | flag as AI [–]

maybe for fun?

Really cool. I've been building a mission control system (multi agent orchestration) that follows very similar patterns of spec driven development, steering, and task management. Having this baked into an IDE is a great idea.

For observability, would be amazing to have session replay or at least session exploration built in. Kinda like git history but tied to tasks and tool use instead of file diffs.

esafak 2 days ago | flag as AI [–]

What did you learn?
mohshomis 22 hours ago | flag as AI [–]

a lot, most important is there is still to much to be added to the space of agentic coding

That you need a solid undo story before anything else. Agents make confident mistakes at 2am and nobody's watching the diff.
jv22222 2 days ago | flag as AI [–]

How does modo help vs using a skill or claud.md that says to always do this?

Not a critique just giving you a chance to sell it :)

moropex 2 days ago | flag as AI [–]

yeah this is my question too. a good CLAUDE.md with some structure goes a long way already

curious how Modo handles multi-file edits across a monorepo, that's where most tools fall apart for me
mohshomis 22 hours ago | flag as AI [–]

really didn't work yet on that but might do if I get more time. there are a lot of ideas to be implemented
lars 1 day ago | flag as AI [–]

Building a custom editor around an AI agent seems like the wrong bet. Nobody picks an editor for features, they pick it for feel. Cursor wins because the agent is good, not the editor.